Research projects

AI-Enhanced HAZOP

AI-Enhanced HAZOP

Our research project is a pioneering endeavor aimed at harnessing the power of Artificial Intelligence (AI) to revolutionize Hazard and Operability (HAZOP) studies and significantly enhance safety measures. \

Autocompletion of engineering diagrams

Autocompletion of engineering diagrams

We propose a novel method enabling autocompletion of engineering diagrams such as flowsheets. This idea is inspired by the autocompletion of text.

Autocorrection of engineering diagrams

Autocorrection of engineering diagrams

Automatically correcting errors is already standard for text documents. We develop this technology for engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs), process flow diagrams (PFDs), or flowsheets.

Automatic generation of P&IDs with Artificial Intelligence

Automatic generation of P&IDs with Artificial Intelligence

We automatically generate engineering diagrams.

Flowsheet digitization

Flowsheet digitization

The goal of flowsheet digitization is to extract the flowsheet topologies from the flowsheet images and save them in a graph format.

Generative artificial intelligence (AI) in chemical process engineering

Generative artificial intelligence (AI) in chemical process engineering

Generative artificial intelligence (AI) is transforming several sectors. This Comment provides a viewpoint outlining the potential significance of generative AI for chemical process engineering. Moreover, challenges for future research and development are outlined.

Graph Neural Networks

Graph Neural Networks

Graph neural networks (GNNs) are a machine learning method that has shown promising results for the prediction of structure-property relationships.

Hybrid modeling

Hybrid modeling

Integrating knowledge into AI is of utmost importance in chemical engineering.

Knowledge graphs

Knowledge graphs

Knowledge graphs link our data in a meaningful way.

Optimization with surrogate models embedded

Optimization with surrogate models embedded

Data-driven surrogate models can learn nonlinear input-output relations and replace expensive simulations or experiments in optimization studies.

Physics-informed machine learning for process modelling and optimization

Physics-informed machine learning for process modelling and optimization

Physics-informed neural networks (PINNs) enforce physical laws that are described by general nonlinear partial differential equations during training. This approach drastically reduces the data demand and prevents overfitting. We explore the potential of physics-informed neural networks in bioengineering.

Self-optimization

Self-optimization

Autonomous reaction platforms and robots are the future of chemistry and biotechnology laboratories.